[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240603112152.GB8496@breakpoint.cc>
Date: Mon, 3 Jun 2024 13:21:52 +0200
From: Florian Westphal <fw@...len.de>
To: Eric Dumazet <edumazet@...gle.com>
Cc: Florian Westphal <fw@...len.de>, netdev@...r.kernel.org,
Paolo Abeni <pabeni@...hat.com>,
"David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>, mleitner@...hat.com,
juri.lelli@...hat.com, vschneid@...hat.com, tglozar@...hat.com,
dsahern@...nel.org, bigeasy@...utronix.de, tglx@...utronix.de
Subject: Re: [PATCH net-next v6 1/3] net: tcp/dcpp: prepare for tw_timer
un-pinning
Eric Dumazet <edumazet@...gle.com> wrote:
> On Mon, Jun 3, 2024 at 11:37 AM Florian Westphal <fw@...len.de> wrote:
> > + spin_lock(lock);
> > + if (timer_shutdown(&tw->tw_timer)) {
> > + /* releases @lock */
> > + __inet_twsk_kill(tw, lock);
> > + } else {
>
> If we do not have a sync variant here, I think that inet_twsk_purge()
> could return while ongoing timers are alive.
Yes.
We can't use sync variant, it would deadlock on ehash spinlock.
> tcp_sk_exit_batch() would then possibly hit :
>
> WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount));
>
> The alive timer are releasing tw->tw_dr->tw_refcount at the end of
> inet_twsk_kill()
Theoretically the tw socket can be unlinked from the tw hash already
(inet_twsk_purge won't encounter it), but timer is still running.
Only solution I see is to schedule() in tcp_sk_exit_batch() until
tw_refcount has dropped to the expected value, i.e. something like
static void tcp_wait_for_tw_timers(struct net *n)
{
while (refcount_read(&n->ipv4.tcp_death_row.tw_refcount) > 1))
schedule();
}
Any better idea?
I started to sketch a patch that keeps PINNED as-is but schedules almost
all of the actual work to a work item.
Idea was that it would lower RT latencies to acceptable level but it got
so ugly that I did not follow this path.
I could resurrect this if you think its worth a try.
Powered by blists - more mailing lists